© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21005
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     모든
    -0.08
     每
    -0.08
     ਹਰ
    -0.08
     at
    -0.08
     一个
    -0.07
    ssel
    -0.07
     ένας
    -0.07
     તમામ
    -0.07
     Chaque
    -0.07
     quatre
    -0.07
    POSITIVE LOGITS
     prompt
    0.16
     description
    0.16
     excerpt
    0.15
     snippet
    0.14
     provided
    0.13
     descrição
    0.13
     ტექ
    0.13
     input
    0.13
     հաղորդ
    0.12
     statement
    0.12
    Activations Density 0.013%

    No Known Activations